ARROW-12936: [C++][Gandiva] Implement ASCII Hive function on Gandiva

jpedroantunes · praveenbingo · commit b0da01de22e1 · 2021-06-07T16:04:29.000+05:30
Implement ASCII Hive function on Gandiva Closes apache#10438 from jpedroantunes/feature/add-ascii and squashes the following commits: 49df145 <João Pedro> Correct linter errors 5bda1e4 <João Pedro> Add projector test for ascii 15e1936 <João Pedro> Add base implementation for ascii Authored-by: João Pedro <joaop@simbioseventures.com> Signed-off-by: Praveen <praveen@dremio.com>
diff --git a/cpp/src/gandiva/function_registry_string.cc b/cpp/src/gandiva/function_registry_string.cc
@@ -62,6 +62,9 @@ std::vector<NativeFunction> GetStringFunctionRegistry() {
       UNARY_SAFE_NULL_NEVER_BOOL_FN(isnull, {}),
       UNARY_SAFE_NULL_NEVER_BOOL_FN(isnotnull, {}),
 
+      NativeFunction("ascii", {}, DataTypeVector{utf8()}, int32(), kResultNullIfNull,
+                     "ascii_utf8"),
+
       NativeFunction("upper", {}, DataTypeVector{utf8()}, utf8(), kResultNullIfNull,
                      "gdv_fn_upper_utf8", NativeFunction::kNeedsContext),
 
diff --git a/cpp/src/gandiva/precompiled/string_ops.cc b/cpp/src/gandiva/precompiled/string_ops.cc
@@ -1214,6 +1214,15 @@ const char* concatOperator_utf8_utf8_utf8_utf8_utf8_utf8_utf8_utf8_utf8_utf8(
   return ret;
 }
 
+// Returns the numeric value of the first character of str.
+GANDIVA_EXPORT
+gdv_int32 ascii_utf8(const char* data, gdv_int32 data_len) {
+  if (data_len == 0) {
+    return 0;
+  }
+  return static_cast<gdv_int32>(data[0]);
+}
+
 FORCE_INLINE
 const char* convert_fromUTF8_binary(gdv_int64 context, const char* bin_in, gdv_int32 len,
                                     gdv_int32* out_len) {
diff --git a/cpp/src/gandiva/precompiled/string_ops_test.cc b/cpp/src/gandiva/precompiled/string_ops_test.cc
@@ -42,6 +42,17 @@ TEST(TestStringOps, TestCompare) {
   EXPECT_GT(mem_compare(left, 7, right, 5), 0);
 }
 
+TEST(TestStringOps, TestAscii) {
+  // ASCII
+  EXPECT_EQ(ascii_utf8("ABC", 3), 65);
+  EXPECT_EQ(ascii_utf8("abc", 3), 97);
+  EXPECT_EQ(ascii_utf8("Hello World!", 12), 72);
+  EXPECT_EQ(ascii_utf8("This is us", 10), 84);
+  EXPECT_EQ(ascii_utf8("", 0), 0);
+  EXPECT_EQ(ascii_utf8("123", 3), 49);
+  EXPECT_EQ(ascii_utf8("999", 3), 57);
+}
+
 TEST(TestStringOps, TestBeginsEnds) {
   // starts_with
   EXPECT_TRUE(starts_with_utf8_utf8("hello sir", 9, "hello", 5));
diff --git a/cpp/src/gandiva/precompiled/types.h b/cpp/src/gandiva/precompiled/types.h
@@ -412,6 +412,8 @@ const char* btrim_utf8_utf8(gdv_int64 context, const char* basetext,
                             gdv_int32 basetext_len, const char* trimtext,
                             gdv_int32 trimtext_len, int32_t* out_len);
 
+gdv_int32 ascii_utf8(const char* data, gdv_int32 data_len);
+
 gdv_int32 locate_utf8_utf8(gdv_int64 context, const char* sub_str, gdv_int32 sub_str_len,
                            const char* str, gdv_int32 str_len);
 
diff --git a/cpp/src/gandiva/tests/utf8_test.cc b/cpp/src/gandiva/tests/utf8_test.cc
@@ -680,4 +680,39 @@ TEST_F(TestUtf8, TestCastVarChar) {
   EXPECT_ARROW_ARRAY_EQUALS(exp, outputs[0]);
 }
 
+TEST_F(TestUtf8, TestAscii) {
+  // schema for input fields
+  auto field0 = field("f0", arrow::utf8());
+  auto schema = arrow::schema({field0});
+
+  // output fields
+  auto field_asc = field("ascii", arrow::int32());
+
+  // Build expression
+  auto asc_expr = TreeExprBuilder::MakeExpression("ascii", {field0}, field_asc);
+
+  std::shared_ptr<Projector> projector;
+  auto status = Projector::Make(schema, {asc_expr}, TestConfiguration(), &projector);
+  EXPECT_TRUE(status.ok()) << status.message();
+
+  // Create a row-batch with some sample data
+  int num_records = 6;
+  auto array0 = MakeArrowArrayUtf8({"ABC", "", "abc", "Hello World", "123", "999"},
+                                   {true, true, true, true, true, true});
+  // expected output
+  auto exp_asc =
+      MakeArrowArrayInt32({65, 0, 97, 72, 49, 57}, {true, true, true, true, true, true});
+
+  // prepare input record batch
+  auto in_batch = arrow::RecordBatch::Make(schema, num_records, {array0});
+
+  // Evaluate expression
+  arrow::ArrayVector outputs;
+  status = projector->Evaluate(*in_batch, pool_, &outputs);
+  EXPECT_TRUE(status.ok()) << status.message();
+
+  // Validate results
+  EXPECT_ARROW_ARRAY_EQUALS(exp_asc, outputs.at(0));
+}
+
 }  // namespace gandiva
